On Wed, Sep 12, 2018 at 09:33:17PM +0200, Jiri Olsa wrote:
> Some of the scheduling tracepoints allow the perf_tp_event
> code to write to ring buffer under different cpu than the
> code is running on.
ARGH.. that is indeed borken.
> diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
> index 4a9937076331..0c976ac414c5 100644
> --- a/kernel/events/ring_buffer.c
> +++ b/kernel/events/ring_buffer.c
> @@ -101,6 +101,7 @@ static void perf_output_put_handle(struct
> perf_output_handle *handle)
>
> out:
> preempt_enable();
> + atomic_set(&rb->recursion, 0);
> }
>
> static __always_inline bool
> @@ -145,6 +146,12 @@ __perf_output_begin(struct perf_output_handle *handle,
> goto out;
> }
>
> + if (atomic_cmpxchg(&rb->recursion, 0, 1) != 0) {
> + if (rb->nr_pages)
> + local_inc(&rb->lost);
> + goto out;
> + }
> +
> handle->rb = rb;
> handle->event = event;
>
> @@ -286,6 +293,7 @@ ring_buffer_init(struct ring_buffer *rb, long watermark,
> int flags)
> rb->overwrite = 1;
>
> atomic_set(&rb->refcount, 1);
> + atomic_set(&rb->recursion, 0);
>
> INIT_LIST_HEAD(&rb->event_list);
> spin_lock_init(&rb->event_lock);
That's not a recursion count, that's a test-and-set spinlock, and you
got the memory ordering wrong for that.
Also, we tried very hard to avoid atomic ops in the ring-buffer and you
just wrecked that. Worse, you wrecked previously working interrupt
nesting output.
Let me have a look at this.
